Naslov
Real-Time Face Tracking under Long-Term Full Occlusions

Autori
Soldić, Martin ; Marčetić, Darijan ; Maračić, Marijo ; Mihalić, Darko ; Ribarić, Slobodan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
10th International Symp osium on Image and Signal Pro cessing and Analysis (ISPA 2017) / Stanislav Kovačič, Sven Lončarić, Matej Kristan, Vitomir Štruc, Mladen Vučić - Zagreb : University of Zagreb, Croatia, 2017, 147-152

ISBN
978-1-5090-4011-7

Skup
10th International Symp osium on Image and Signal Pro cessing and Analysis (ISPA 2017)

Mjesto i datum
Ljubljana, Slovenija, 18.09.2017. - 20.09.2017

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
tracking, long-term full occlusion, re-tracking, correlation filter, face

Sažetak
The identified weaknesses of most of state-of-the-art trackers are inability to cope with long-term full occlusions, abrupt motion, detecting and tracking a reappeared target. In this paper, we present a robust real-time single face tracking system with several new key features: semi-automatic target tracking initialization based on a robust face detector, an effective target loss estimation based on a response of a position correlation filter, a candidate image patch selection for reinitialization supported with a short- and long-term memories (STM and LTM). These memories are used for tracking reinitialization during online learning procedure. The STM is used to select an image patch as candidate for re-tracking based on stored position correlation filters (from current frame) in case of short-term full occlusions, while the LTM stores aggregated position correlation filters (online learned) is used to recover the tracker from long-term full occlusions. Validation of the tracking system was performed by evaluation on a subset of videos from Online Tracking Benchmark (OTB) dataset and our own video.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA